5 matches found
GHSA-H3RC-J82P-2C3H vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE
Summary In vLLM 0.30.0, ImageMediaIO passes attacker-controlled image bytes to Pillow's format autodetection without restricting the accepted formats; the request's MIME label does not constrain decoder selection. An EPS payload labeled image/png reached the host's Ghostscript executable. On a ho...
CVE-2026-115915 vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE
vLLM is an inference and serving engine for large language models. Prior to 0.32.0, ImageMediaIO passes attacker-controlled image bytes to Pillow through Image.openBytesIOdata without restricting decoder selection, and the MIME label does not constrain the selected format. Image-capable request...
CVE-2026-115915 vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE
vLLM is an inference and serving engine for large language models. Prior to 0.32.0, ImageMediaIO passes attacker-controlled image bytes to Pillow through Image.openBytesIOdata without restricting decoder selection, and the MIME label does not constrain the selected format. Image-capable request...
CVE-2026-115915 vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE
vLLM is an inference and serving engine for large language models. Prior to 0.32.0, ImageMediaIO passes attacker-controlled image bytes to Pillow through Image.openBytesIOdata without restricting decoder selection, and the MIME label does not constrain the selected format. Image-capable request...
CVE-2026-115915
The vLLM inference engine (prior to version 0.32.0 ) is vulnerable because ImageMediaIO passes attacker-controlled image bytes to Pillow via Image.open(BytesIO(data)) without restricting decoder selection or constraining formats via MIME labels. Attackers can submit specially crafted images, such...